Trust Assessment
fullbackup received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill requires root-level access for backup operations.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requires root-level access for backup operations The skill `fullbackup` is designed to execute shell scripts located under `/root/.openclaw/workspace/scripts/` and store backup archives in `/root/.openclaw/backups`. This implies the skill expects to run with root or highly privileged user permissions. Granting such broad access to an AI agent skill, especially one that acts as a wrapper for another script, constitutes excessive permissions. A vulnerability in the underlying `backup-local.sh` script (which is not provided for analysis) could be exploited with full system privileges. Review the necessity of running this skill with root privileges. If possible, refactor the backup process to operate with a dedicated, least-privilege user account and restrict access to only the necessary directories. Ensure the `backup-local.sh` script is thoroughly audited for vulnerabilities, as any exploit would run with elevated permissions. | LLM | scripts/full-backup.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/b756f1a0e0bea2ec)
Powered by SkillShield